yt-dlc/youtube_dl/extractor/mtv.py

491 lines
18 KiB
Python
Raw Normal View History

2014-01-22 00:07:02 +01:00
from __future__ import unicode_literals
2013-06-23 21:34:03 +02:00
import re
2015-02-18 18:27:45 +01:00
from .common import InfoExtractor
from ..compat import (
2015-01-30 16:57:59 +01:00
compat_str,
compat_xpath,
)
from ..utils import (
2013-06-23 21:34:03 +02:00
ExtractorError,
find_xpath_attr,
2014-01-20 22:11:34 +01:00
fix_xml_ampersands,
float_or_none,
HEADRequest,
RegexNotFoundError,
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 17:18:17 +01:00
sanitized_Request,
2016-07-17 11:56:39 +02:00
strip_or_none,
timeconvert,
try_get,
unescapeHTML,
update_url_query,
url_basename,
xpath_text,
2013-06-23 21:34:03 +02:00
)
def _media_xml_tag(tag):
return '{http://search.yahoo.com/mrss/}%s' % tag
2013-06-23 21:34:03 +02:00
2015-02-18 18:27:45 +01:00
class MTVServicesInfoExtractor(InfoExtractor):
_MOBILE_TEMPLATE = None
_LANG = None
@staticmethod
def _id_from_uri(uri):
return uri.split(':')[-1]
@staticmethod
def _remove_template_parameter(url):
# Remove the templates, like &device={device}
return re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', url)
def _get_feed_url(self, uri):
return self._FEED_URL
def _get_thumbnail_url(self, uri, itemdoc):
search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
thumb_node = itemdoc.find(search_path)
if thumb_node is None:
return None
2017-07-23 16:00:19 +02:00
return thumb_node.get('url') or thumb_node.text or None
def _extract_mobile_video_formats(self, mtvn_id):
webpage_url = self._MOBILE_TEMPLATE % mtvn_id
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 17:18:17 +01:00
req = sanitized_Request(webpage_url)
# Otherwise we get a webpage that would execute some javascript
req.add_header('User-Agent', 'curl/7')
webpage = self._download_webpage(req, mtvn_id,
2014-11-23 21:39:15 +01:00
'Downloading mobile page')
metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url'))
req = HEADRequest(metrics_url)
response = self._request_webpage(req, mtvn_id, 'Resolving url')
url = response.geturl()
# Transform the url to get the best quality:
url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1)
2014-11-23 20:41:03 +01:00
return [{'url': url, 'ext': 'mp4'}]
def _extract_video_formats(self, mdoc, mtvn_id, video_id):
if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4|copyright_error\.flv(?:\?geo\b.+?)?)$', mdoc.find('.//src').text) is not None:
if mtvn_id is not None and self._MOBILE_TEMPLATE is not None:
self.to_screen('The normal version is not available from your '
2014-11-23 21:39:15 +01:00
'country, trying with the mobile version')
return self._extract_mobile_video_formats(mtvn_id)
raise ExtractorError('This video is not available from your country.',
2014-11-23 21:39:15 +01:00
expected=True)
2013-10-04 11:10:04 +02:00
formats = []
for rendition in mdoc.findall('.//rendition'):
if rendition.get('method') == 'hls':
hls_url = rendition.find('./src').text
2017-01-10 16:31:20 +01:00
formats.extend(self._extract_m3u8_formats(
hls_url, video_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
else:
# fms
try:
_, _, ext = rendition.attrib['type'].partition('/')
rtmp_video_url = rendition.find('./src').text
if 'error_not_available.swf' in rtmp_video_url:
raise ExtractorError(
'%s said: video is not available' % self.IE_NAME,
expected=True)
if rtmp_video_url.endswith('siteunavail.png'):
continue
formats.extend([{
'ext': 'flv' if rtmp_video_url.startswith('rtmp') else ext,
'url': rtmp_video_url,
'format_id': '-'.join(filter(None, [
'rtmp' if rtmp_video_url.startswith('rtmp') else None,
rendition.get('bitrate')])),
'width': int(rendition.get('width')),
'height': int(rendition.get('height')),
}])
except (KeyError, TypeError):
raise ExtractorError('Invalid rendition field.')
if formats:
self._sort_formats(formats)
2013-10-04 11:10:04 +02:00
return formats
2015-01-30 16:57:59 +01:00
def _extract_subtitles(self, mdoc, mtvn_id):
subtitles = {}
for transcript in mdoc.findall('.//transcript'):
if transcript.get('kind') != 'captions':
continue
lang = transcript.get('srclang')
for typographic in transcript.findall('./typographic'):
sub_src = typographic.get('src')
if not sub_src:
continue
ext = typographic.get('format')
if ext == 'cea-608':
ext = 'scc'
subtitles.setdefault(lang, []).append({
'url': compat_str(sub_src),
'ext': ext
})
2015-02-18 18:27:45 +01:00
return subtitles
2015-01-30 16:57:59 +01:00
def _get_video_info(self, itemdoc, use_hls=True):
uri = itemdoc.find('guid').text
video_id = self._id_from_uri(uri)
self.report_extraction(video_id)
2016-02-19 20:56:45 +01:00
content_el = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content')))
mediagen_url = self._remove_template_parameter(content_el.attrib['url'])
mediagen_url = mediagen_url.replace('device={device}', '')
if 'acceptMethods' not in mediagen_url:
mediagen_url += '&' if '?' in mediagen_url else '?'
mediagen_url += 'acceptMethods='
mediagen_url += 'hls' if use_hls else 'fms'
mediagen_doc = self._download_xml(
mediagen_url, video_id, 'Downloading video urls', fatal=False)
if mediagen_doc is False:
return None
item = mediagen_doc.find('./video/item')
if item is not None and item.get('type') == 'text':
message = '%s returned error: ' % self.IE_NAME
if item.get('code') is not None:
message += '%s - ' % item.get('code')
message += item.text
raise ExtractorError(message, expected=True)
2016-07-17 11:56:39 +02:00
description = strip_or_none(xpath_text(itemdoc, 'description'))
2013-10-04 11:10:04 +02:00
timestamp = timeconvert(xpath_text(itemdoc, 'pubDate'))
title_el = None
if title_el is None:
title_el = find_xpath_attr(
itemdoc, './/{http://search.yahoo.com/mrss/}category',
'scheme', 'urn:mtvn:video_title')
if title_el is None:
title_el = itemdoc.find(compat_xpath('.//{http://search.yahoo.com/mrss/}title'))
2014-02-11 19:07:30 +01:00
if title_el is None:
title_el = itemdoc.find(compat_xpath('.//title'))
if title_el.text is None:
title_el = None
title = title_el.text
if title is None:
raise ExtractorError('Could not find video title')
title = title.strip()
# This a short id that's used in the webpage urls
mtvn_id = None
mtvn_id_node = find_xpath_attr(itemdoc, './/{http://search.yahoo.com/mrss/}category',
2014-11-23 21:39:15 +01:00
'scheme', 'urn:mtvn:id')
if mtvn_id_node is not None:
mtvn_id = mtvn_id_node.text
formats = self._extract_video_formats(mediagen_doc, mtvn_id, video_id)
# Some parts of complete video may be missing (e.g. missing Act 3 in
# http://www.southpark.de/alle-episoden/s14e01-sexual-healing)
if not formats:
return None
self._sort_formats(formats)
return {
'title': title,
'formats': formats,
2015-01-30 16:57:59 +01:00
'subtitles': self._extract_subtitles(mediagen_doc, mtvn_id),
2013-10-04 11:10:04 +02:00
'id': video_id,
'thumbnail': self._get_thumbnail_url(uri, itemdoc),
'description': description,
2016-02-19 20:56:45 +01:00
'duration': float_or_none(content_el.attrib.get('duration')),
'timestamp': timestamp,
2013-10-04 11:10:04 +02:00
}
def _get_feed_query(self, uri):
data = {'uri': uri}
if self._LANG:
data['lang'] = self._LANG
return data
def _get_videos_info(self, uri, use_hls=True):
video_id = self._id_from_uri(uri)
feed_url = self._get_feed_url(uri)
info_url = update_url_query(feed_url, self._get_feed_query(uri))
return self._get_videos_info_from_url(info_url, video_id, use_hls)
2015-08-28 17:24:54 +02:00
def _get_videos_info_from_url(self, url, video_id, use_hls=True):
idoc = self._download_xml(
2015-08-28 17:24:54 +02:00
url, video_id,
2014-01-22 00:07:02 +01:00
'Downloading info', transform_source=fix_xml_ampersands)
title = xpath_text(idoc, './channel/title')
description = xpath_text(idoc, './channel/description')
entries = []
for item in idoc.findall('.//item'):
info = self._get_video_info(item, use_hls)
if info:
entries.append(info)
return self.playlist_result(
entries, playlist_title=title, playlist_description=description)
2013-06-23 21:34:03 +02:00
def _extract_triforce_mgid(self, webpage, data_zone=None, video_id=None):
triforce_feed = self._parse_json(self._search_regex(
r'triforceManifestFeed\s*=\s*({.+?})\s*;\s*\n', webpage,
'triforce feed', default='{}'), video_id, fatal=False)
data_zone = self._search_regex(
r'data-zone=(["\'])(?P<zone>.+?_lc_promo.*?)\1', webpage,
'data zone', default=data_zone, group='zone')
feed_url = try_get(
triforce_feed, lambda x: x['manifest']['zones'][data_zone]['feed'],
compat_str)
if not feed_url:
return
feed = self._download_json(feed_url, video_id, fatal=False)
if not feed:
return
return try_get(feed, lambda x: x['result']['data']['id'], compat_str)
def _extract_mgid(self, webpage):
try:
# the url can be http://media.mtvnservices.com/fb/{mgid}.swf
# or http://media.mtvnservices.com/{mgid}
og_url = self._og_search_video_url(webpage)
mgid = url_basename(og_url)
if mgid.endswith('.swf'):
mgid = mgid[:-4]
except RegexNotFoundError:
2014-07-13 13:15:18 +02:00
mgid = None
if mgid is None or ':' not in mgid:
mgid = self._search_regex(
2017-10-09 18:50:53 +02:00
[r'data-mgid="(.*?)"', r'swfobject\.embedSWF\(".*?(mgid:.*?)"'],
webpage, 'mgid', default=None)
if not mgid:
sm4_embed = self._html_search_meta(
'sm4:video:embed', webpage, 'sm4 embed', default='')
mgid = self._search_regex(
r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=None)
if not mgid:
mgid = self._extract_triforce_mgid(webpage)
return mgid
2015-01-30 16:57:59 +01:00
def _real_extract(self, url):
title = url_basename(url)
webpage = self._download_webpage(url, title)
mgid = self._extract_mgid(webpage)
2015-01-30 16:57:59 +01:00
videos_info = self._get_videos_info(mgid)
return videos_info
class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
IE_NAME = 'mtvservices:embedded'
_VALID_URL = r'https?://media\.mtvnservices\.com/embed/(?P<mgid>.+?)(\?|/|$)'
_TEST = {
# From http://www.thewrap.com/peter-dinklage-sums-up-game-of-thrones-in-45-seconds-video/
'url': 'http://media.mtvnservices.com/embed/mgid:uma:video:mtv.com:1043906/cp~vid%3D1043906%26uri%3Dmgid%3Auma%3Avideo%3Amtv.com%3A1043906',
'md5': 'cb349b21a7897164cede95bd7bf3fbb9',
'info_dict': {
'id': '1043906',
'ext': 'mp4',
'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds',
'description': '"Sexy sexy sexy, stabby stabby stabby, beautiful language," says Peter Dinklage as he tries summarizing "Game of Thrones" in under a minute.',
'timestamp': 1400126400,
'upload_date': '20140515',
},
}
@staticmethod
def _extract_url(webpage):
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media.mtvnservices.com/embed/.+?)\1', webpage)
if mobj:
return mobj.group('url')
def _get_feed_url(self, uri):
video_id = self._id_from_uri(uri)
config = self._download_json(
'http://media.mtvnservices.com/pmt/e1/access/index.html?uri=%s&configtype=edge' % uri, video_id)
return self._remove_template_parameter(config['feedWithQueryParams'])
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
mgid = mobj.group('mgid')
return self._get_videos_info(mgid)
class MTVIE(MTVServicesInfoExtractor):
IE_NAME = 'mtv'
_VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|(?:full-)?episodes)/(?P<id>[^/?#.]+)'
_FEED_URL = 'http://www.mtv.com/feeds/mrss/'
_TESTS = [{
'url': 'http://www.mtv.com/video-clips/vl8qof/unlocking-the-truth-trailer',
'md5': '1edbcdf1e7628e414a8c5dcebca3d32b',
'info_dict': {
'id': '5e14040d-18a4-47c4-a582-43ff602de88e',
'ext': 'mp4',
'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer',
'description': '"Unlocking the Truth" premieres August 17th at 11/10c.',
'timestamp': 1468846800,
'upload_date': '20160718',
},
}, {
'url': 'http://www.mtv.com/full-episodes/94tujl/unlocking-the-truth-gates-of-hell-season-1-ep-101',
'only_matching': True,
}, {
'url': 'http://www.mtv.com/episodes/g8xu7q/teen-mom-2-breaking-the-wall-season-7-ep-713',
'only_matching': True,
}]
2017-01-28 14:29:22 +01:00
class MTV81IE(InfoExtractor):
IE_NAME = 'mtv81'
_VALID_URL = r'https?://(?:www\.)?mtv81\.com/videos/(?P<id>[^/?#.]+)'
_TEST = {
'url': 'http://www.mtv81.com/videos/artist-to-watch/the-godfather-of-japanese-hip-hop-segment-1/',
'md5': '1edbcdf1e7628e414a8c5dcebca3d32b',
'info_dict': {
'id': '5e14040d-18a4-47c4-a582-43ff602de88e',
'ext': 'mp4',
'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer',
'description': '"Unlocking the Truth" premieres August 17th at 11/10c.',
'timestamp': 1468846800,
'upload_date': '20160718',
},
}
def _extract_mgid(self, webpage):
return self._search_regex(
r'getTheVideo\((["\'])(?P<id>mgid:.+?)\1', webpage,
'mgid', group='id')
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
mgid = self._extract_mgid(webpage)
return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid)
class MTVVideoIE(MTVServicesInfoExtractor):
IE_NAME = 'mtv:video'
_VALID_URL = r'''(?x)^https?://
(?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$|
m\.mtv\.com/videos/video\.rbml\?.*?id=(?P<mgid>[^&]+))'''
_FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/'
_TESTS = [
{
2014-01-22 00:07:02 +01:00
'url': 'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
'md5': '850f3f143316b1e71fa56a4edfd6e0f8',
'info_dict': {
2015-02-01 12:08:21 +01:00
'id': '853555',
'ext': 'mp4',
2014-01-22 00:07:02 +01:00
'title': 'Taylor Swift - "Ours (VH1 Storytellers)"',
'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
'timestamp': 1352610000,
'upload_date': '20121111',
},
},
]
def _get_thumbnail_url(self, uri, itemdoc):
return 'http://mtv.mtvnimages.com/uri/' + uri
2013-06-23 21:34:03 +02:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
uri = mobj.groupdict().get('mgid')
if uri is None:
webpage = self._download_webpage(url, video_id)
2014-11-23 20:41:03 +01:00
# Some videos come from Vevo.com
2015-02-01 12:08:21 +01:00
m_vevo = re.search(
r'(?s)isVevoVideo = true;.*?vevoVideoId = "(.*?)";', webpage)
if m_vevo:
2014-11-23 21:20:46 +01:00
vevo_id = m_vevo.group(1)
2014-01-22 00:07:02 +01:00
self.to_screen('Vevo video detected: %s' % vevo_id)
return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
2014-11-23 20:41:03 +01:00
2014-01-22 00:07:02 +01:00
uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, 'uri')
return self._get_videos_info(uri)
class MTVDEIE(MTVServicesInfoExtractor):
IE_NAME = 'mtv.de'
2015-08-28 17:41:54 +02:00
_VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P<id>\d+)-[^/#?]+/*(?:[#?].*)?$'
2015-08-28 17:24:54 +02:00
_TESTS = [{
'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum',
'info_dict': {
'id': 'music_video-a50bc5f0b3aa4b3190aa',
'ext': 'flv',
2015-08-28 17:24:54 +02:00
'title': 'MusicVideo_cro-traum',
'description': 'Cro - Traum',
},
2015-08-28 17:24:54 +02:00
'params': {
# rtmp download
'skip_download': True,
},
2016-07-26 07:19:47 +02:00
'skip': 'Blocked at Travis CI',
}, {
# mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97)
'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen',
'info_dict': {
'id': 'local_playlist-f5ae778b9832cc837189',
'ext': 'flv',
'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1',
},
'params': {
# rtmp download
'skip_download': True,
},
2016-07-26 07:19:47 +02:00
'skip': 'Blocked at Travis CI',
2015-08-28 17:41:54 +02:00
}, {
'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3',
'info_dict': {
'id': 'local_playlist-4e760566473c4c8c5344',
'ext': 'mp4',
'title': 'Article_mtv-movies-spotlight-pixels-teil-3_short-clips_part1',
'description': 'MTV Movies Supercut',
},
'params': {
# rtmp download
'skip_download': True,
},
'skip': 'Das Video kann zur Zeit nicht abgespielt werden.',
2015-08-28 17:24:54 +02:00
}]
def _real_extract(self, url):
2015-08-28 17:24:54 +02:00
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
playlist = self._parse_json(
self._search_regex(
r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'),
video_id)
def _mrss_url(item):
return item['mrss'] + item.get('mrssvars', '')
2015-08-28 17:41:54 +02:00
# news pages contain single video in playlist with different id
if len(playlist) == 1:
return self._get_videos_info_from_url(_mrss_url(playlist[0]), video_id)
2015-08-28 17:41:54 +02:00
for item in playlist:
2015-08-28 17:24:54 +02:00
item_id = item.get('id')
if item_id and compat_str(item_id) == video_id:
return self._get_videos_info_from_url(_mrss_url(item), video_id)